检索结果-内蒙古大学图书馆

5th IEEE International Conference on Communications, Information, Electronic and Energy Systems, CIEES 2024

作者： Karapidakis, Emmanuel Markaki, Marini Apostolakis, Spyridon Canizes, Bruno Androulakis, Radamanthys Castro, Fabio Hellenic Mediterranean University Electrical and Computer Engineering Department Heraklion Greece Polytechnic Institute of Porto GECAD - Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development Porto Portugal ECTE GECAD - Research Group on Research Department Rethymno Greece

ISBN: (纸本)9798350352863

With the rise of smart buildings, new expertise gaps and security vulnerabilities are emerging, necessitating a comprehensive understanding of their current state and proactive future planning to address these challenges. Such identification is crucial for mapping the pathway towards vocational modernization (keeping up with trends and goal alignment). To assess these gaps, this paper explores the extensive literature that draws on workshops, expert interviews, and research to identify emerging roles and training needs across seven countries: Greece, Spain, Portugal, Italy, North Macedonia, Germany, and the Netherlands. In particular, it examines the validity of its findings in critical areas such as security, privacy, and the integration of smart grids with energy markets. Additionally, the paper highlights future skills gaps emerging from advancements in IoT, automation, and renewable energy technologies. It emphasizes the growing demand for specialized electrical expertise to optimize energy production, integrate monitoring and storage systems, and manage electric vehicle charging and energy communities effectively. In conclusion, the study identifies critical gaps in expertise and training needed to keep up with the rapid evolution of smart building technologies. Emerging trends highlight the demand for interdisciplinary skills, particularly in IoT, automation, and renewable energy. As these fields advance, expertise in cybersecurity, energy management, and smart grid integration will be crucial, emphasizing the need for proactive workforce development and planning. The findings can be used to inform and direct policymakers towards the smooth reexamination of vocational training. © 2024 IEEE.

关键词： Power grids

来源：评论

学校读者我要写书评

暂无评论

Learning-Based Design of Off-Policy Gaussian Controllers: Integrating Model Predictive Control and Gaussian Process Regression

arXiv

引用

arXiv 2024年

作者： Tekumatla, Shiva Kumar Gampa, Varun Farzan, Siavash The Robotics Engineering Department Worcester Polytechnic Institute WorcesterMA01609 United States The Electrical Engineering Department California Polytechnic State University San Luis ObispoCA93407 United States

This paper presents an off-policy Gaussian Predictive Control (GPC) framework aimed at solving optimal control problems with a smaller computational footprint, thereby facilitating real-time applicability while ensuring critical safety considerations. The proposed controller imitates classical control methodologies by modeling the optimization process through a Gaussian process and employs Gaussian Process Regression to learn from the Model Predictive Control (MPC) algorithm. Notably, the Gaussian Process setup does not incorporate a built-in model, enhancing its applicability to a broad range of control problems. We applied this framework experimentally to a differential drive mobile robot, tasking it with trajectory tracking and obstacle avoidance. Leveraging the off-policy aspect, the controller demonstrated adaptability to diverse trajectories and obstacle behaviors. Simulation experiments confirmed the effectiveness of the proposed GPC method, emphasizing its ability to learn the dynamics of optimal control strategies. Consequently, our findings highlight the significant potential of off-policy Gaussian Predictive Control in achieving real-time optimal control for handling of robotic systems in safety-critical scenarios. Copyright © 2024, The Authors. All rights reserved.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Data Driven Methods to Predict Vertical Profiles of the Rails: A Case Study 10

Data Driven Methods to Predict Vertical Profiles of the Rail...

引用

10th International Conference on ICT for Smart Society, ICISS 2023

作者： Nugraha, Ade Chandra Supangkat, Suhono Harso Nugraha, Igb Baskara Handoko, Yunendar Aryo Purwadinata, Awan Hermawan Saputro, Dimas Wisnu Bandung State of Polytechnic School of Electrical Engineering and Informatics Bandung Institute of Technology Department of Computer Engineering and Informatics Bandung Indonesia School of Electrical Engineering and Informatics Bandung Institute of Technology Smart City and Community Innovation Center Bandung Indonesia Bandung Institute of Technology Faculty of Mechanical and Aerospace Engineering Bandung Indonesia PT Kereta Api Indonesia Managing Director of Infrastructure Bandung Indonesia Bandung State of Polytechnic Department of Computer Engineering and Informatics Bandung Indonesia

ISBN: (纸本)9798350339543

Predicting the value of railroad track geometry is needed to reduce the cost and time of rail condition measurements that have been carried out periodically every three months by railroad operators in Indonesia (PT Kereta Api Indonesia/PT KAI). Four track geometry parameters - vertical profile, horizontal alignment, twist, and gauge - are the reference measurements that will be mapped with alternative measurement results using accelerometers installed on regular trains (in-service trains). In this paper, eight prediction algorithms from the machine learning model are applied to map the vertical profile with 73 kilometers of measurement data in the Jakarta to Padalarang railroad segment, precisely on the Jatinegara-Cikampek measuring trip conducted from April 2019 to June 2022. The evaluation performance of the prediction results has been measured with the GadientBoosting Regressor algorithm is the best algorithm with MSE = 0.791, R2 = 0.507 and feature importance on the Train speed and Az attributes. The research can be continued to detect the correlation of three other track geometry parameters referring to the dataset of rail geometry condition measurement results through accelerometers on regular trains (in-service trains). © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Board 87: Work in Progress: The 2TO4 Project - Facilitated Transition from 2-Year to 4-Year electrical and computer engineering Studies

Board 87: Work in Progress: The 2TO4 Project - Facilitated T...

引用

2024 ASEE Annual Conference and Exposition

作者： Connor, Kenneth A. Chouikha, Mohamed F. Velez-Reyes, Miguel Sullivan, Barry J. Berhane, Bruk T. Klein, Michelle Gullie, Kathy Ann Muskett, Milford Inclusive Engineering Consortium Rensselaer Polytechnic Institute United States Prairie View A&M University United States University of Texas El Paso United States Electrical & Computer Engineering Department United States Florida International University United States Electrical and Computer Engineering Dept. United States Services LLC United States

The IEC is a nonprofit organization that enables collective efforts through equitable partnerships between its 21 MSI core members, 14 PWI affiliate members and 7 corporate members. The IEC 2TO4 Project builds on its Pathways to Success program to support students who begin their studies at a community college or other 2-year institution by providing financial support (scholarships, internships, academic year stipends), mentoring and other personalized transition support, professional guidance, and community engagement. The 2TO4 network of community colleges (CCs) consists of 20 sub-networks built around the 20 4-year HBCUs, HSIs and TCUs that form most of the core membership of IEC. Generally, a small number (1-3) of CCs located near a core member educate a few students who transfer to the local 4-year MSI ECE program. Some IEC core members have well-developed relationships with their local CCs and see much larger numbers of transfer students. The vision of 2TO4 is to double the total number of students following this pathway to their BS degree in ECE by sharing promising practices and providing robust transition support infrastructure and increased financial support for those CC students who should have MSIs on their radar as they complete their associate degrees. Participating CCs become members of IEC and engage in equitable partnerships with 4-year MSIs and PWIs, industry and DoD labs to implement the various building blocks of 2TO4. During the first year of this multi-year effort, a base version of 2TO4 was created. Program leadership connected with DoDSTEM and the other CC programs it funds, defining the parameters of 2TO4 1.0 (formalizing the relationship between MSI core members and their key local CCs), and began working through institutional challenges with the 60+ program partners. Regular meetings were scheduled, and a general communication infrastructure was rolled out. The first cohort of more than two dozen student participants was selected along wit

关键词： Nonprofit organization

来源：评论

学校读者我要写书评

暂无评论

Three-way trade-off in multi-objective learning: optimization, generalization and conflict-avoidance

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 9153-9205页

作者： Lisha Chen Heshan Fernando Yiming Ying Tianyi Chen Department of Electrical Computer & Systems Engineering Rensselaer Polytechnic Institute School of Mathematics and Statistics University of Sydney NSW Australia

Multi-objective learning (MOL) often arises in machine learning problems when there are multiple data modalities or tasks. One critical challenge in MOL is the potential conflict among different objectives during the optimization process. Recent works have developed various dynamic weighting algorithms for MOL, where the central idea is to find an update direction that avoids conflicts among objectives. Albeit its appealing intuition, empirical studies show that dynamic weighting methods may not outperform static ones. To understand this theory-practice gap, we focus on a stochastic variant of MGDA, the Multi-objective gradient with Double sampling (MoDo), and study the generalization performance and its interplay with optimization through the lens of algorithmic stability in the framework of statistical learning theory. We find that the key rationale behind MGDA--updating along conflict-avoidant direction--may hinder dynamic weighting algorithms from achieving the optimal O(1/√n) population risk, where n is the number of training samples. We further demonstrate the impact of dynamic weights on the three-way trade-off among optimization, generalization, and conflict avoidance unique in MOL. We showcase the generality of our theoretical framework by analyzing other algorithms under the framework. Experiments on various multi-task learning benchmarks are performed to demonstrate the practical applicability. Code is available at https://***/heshandevaka/Trade-Off-MOL.

关键词： multi-objective optimization statistical learning theory algorithm stability Pareto stationarity gradient conflict

来源：评论

学校读者我要写书评

暂无评论

Modular Multilevel Converters-Part I: Modeling Based on State-Plane Analysis 48

Modular Multilevel Converters-Part I: Modeling Based on Stat...

引用

48th Annual Conference of the IEEE Industrial Electronics Society, IECON 2022

作者： Hsieh, Yi-Hsun Lee, Fred C. Virginia Polytechnic Institute and State University The Bradley Department of Electrical and Computer Engineering BlacksburgVA United States

ISBN: (数字)9781665480253

ISBN: (纸本)9781665480253

Modular multilevel converter is deemed the solution for high-voltage high-power applications. The introduction of capacitor to each arm leads to complicated power flow and thus complicated control scheme. Without a proper control, this often results in large circulating energy. The state plane analysis identified the two types of circulating energies, one related to the power difference between input and output, and the other related to the internal power swapping. Due to their orthogonal nature, a coordinate transformation is proposed, which leads to a decoupled equivalent circuit model. The proposed model suggests two control laws, aiming at eliminating both types of circulating energy. © 2022 IEEE.

关键词： Circuit simulation

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potential of Transfer Learning for Accurate Segmentation of Pathological Structures in X-Ray Images 2

Exploring the Potential of Transfer Learning for Accurate Se...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Kishore, Lalit Shaikh, M.Z. Goel, Pawan Kumar Badhoutiya, Arti SRMIST Delhi Ncr Department of Computer Application UPGhaziabad Modinagar India Shree Bhagubhai Mafatlal Polytechnic College Department of Electronics & Telecommunication Maharastra Mumbai India Raj Kumar Goel Institute of Technology Department of Computer Science & Engineering UP Ghaziabad India Gla University Department of Electrical Engineering UP Mathura India

ISBN: (纸本)9798350371055

This paper explores the capability of transfer learning for the correct segmentation of pathological systems in X-ray pictures. Switch mastering is a way in gadget mastering wherein understanding received from a source challenge is transferred to an extraordinary goal task to enhance performance. This paper specializes in how transfer getting to know may be applied to segmenting pathological systems in X-ray photos. The paper discusses the proposed technique's overall performance on datasets from public medical resources gathered from healthy and diseased lungs and stomach organs. The experiments used in this paper display that with the resource of pre-educated models in transfer getting to know, the performance of the segmentation of the pathological regions in X-ray photos may be stepped forward. Eventually, the paper outlines the ability of transfer mastering for clinical picture segmentation and discusses how it can be further progressed in the future. © 2024 IEEE.

关键词： Healthy Pathological Potential And Medical Transfer

来源：评论

学校读者我要写书评

暂无评论

Human-Led Robotic Transportation of Elastic Objects with Adaptive Control 9

Human-Led Robotic Transportation of Elastic Objects with Ada...

引用

9th International Conference on Robotics and Automation engineering, ICRAE 2024

作者： Cui, Zhenxi Lai, Jiewen Lu, Bo Guo, Yi Chu, Henry K. University of West London School of Computing and Engineering London United Kingdom Chinese University of Hong Kong Department of Electronic Engineering Hong Kong Soochow University School of Mechanical and Electrical Engineering Suzhou China Stevens Institute of Technology Department of Electrical and Computer Engineering HobokenNJ United States The Hong Kong Polytechnic University Department of Mechanical Engineering Hong Kong

ISBN: (纸本)9798331518301

The perception and transportation of soft objects are critical tasks in daily life, and recent sensor advancements enable robots to safely perform these tasks in human-shared environments. This study advances elastic linear object transportation by introducing a collaborative framework where a human leads, providing task-specific instructions to guide the robot. Unlike conventional methods focused on fixed object manipulation, our approach dynamically controls and converges feature points of the elastic object into desired configurations during transportation. We developed an online model estimation technique using a least-squares optimization algorithm, with an exponential forgetting mechanism to adaptively update the model under disturbances from sensors and human interaction. Validated in experiments with a 6-DOF robot and depth camera, our method demonstrated robustness across varied scenarios, achieving faster convergence and reduced positional fluctuation compared to conventional gradient descent approaches. © 2024 IEEE.

关键词： Adaptive control systems

来源：评论

学校读者我要写书评

暂无评论

Modular Multilevel Converters-Part II: Control Based on Decoupled Equivalent Circuit Model 48

Modular Multilevel Converters-Part II: Control Based on Deco...

引用

48th Annual Conference of the IEEE Industrial Electronics Society, IECON 2022

作者： Hsieh, Yi-Hsun Lee, Fred C. Virginia Polytechnic Institute and State University The Bradley Department of Electrical and Computer Engineering BlacksburgVA United States

ISBN: (数字)9781665480253

ISBN: (纸本)9781665480253

Since there are less control means than state variables to be controlled, the modular multilevel converter is an overly-constrained system. The minimum circulating energy was unknown, and the control implementation to address this challenge was vague. In Part I, two types of circulating energy with orthogonal nature are identified though state-space analysis: one related to instantaneous input and output power unbalance, and the other related to internal power swapping. The corresponding decoupled equivalent circuit based on the proposed coordinate transformation was presented, which leads to two control laws aiming at eliminating each type of circulating energy. In Part II, the convoluted multi-state-variable is clearly explained using the proposed equivalent circuit model. The two control laws and the state planes are utilized to evaluate the effectiveness of the existing control methods. © 2022 IEEE.

关键词： Equivalent circuits

来源：评论

学校读者我要写书评

暂无评论

Design of a High-Precision Inverter-Based CMOS Comparator for High Accuracy Applications

Design of a High-Precision Inverter-Based CMOS Comparator fo...

引用

Midwest Symposium on Circuits and Systems (MWSCAS)

作者： Amr M. Maghraby Ibrahim Bozyel Islam T. Abougindia Suat U. Ay Department of Electrical & Computer Engineering University of Idaho Moscow USA Department of Electronics Engineering Military Technical College EGYPT Department of Electrical & Computer Engineering Worcester Polytechnique Institute USA

ISBN: (数字)9798350387179

ISBN: (纸本)9798350387186

A new low-power, high-precision inverter-based CMOS comparator is introduced in this paper. Inherent high-power consumption of CMOS inverter is controlled by a current-limiting circuit. A current-modulation technique is proposed to maximize the gain of the comparator before making its decision. The comparator uses two unfolded inverters and a sampling circuit to complete its operation. The current-modulation circuit uses a programmable current mirror and a 5-bit counter without adding much power to the original circuit. An auxiliary comparator and a reference generator are implemented to control the current modulation operation. The circuit presented addresses the gain error resulting from charge injection in the inverter and corrects the error arising from incorrect reset operation. The circuit was simulated in a standard 180nm CMOS process. Simulations show up to 3x improvement of the comparator's gain with very high precision. Only one calibration circuit is required for any number of comparators; hence, this technique can be used to achieve high-resolntion ADCs.

关键词： Semiconductor device modeling Power demand Current mirrors Circuits and systems Modulation Inverters Generators

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：